The effect of student self-described learning styles within two models of teaching in an introductory data mining course

Abstract

This paper examines the roles of learning styles and models of teaching within a data mining educational program designed for undergraduate, non-computer science college students. The experimental design is framed by a discussion of data mining education to date and a vision for its future. Little research has been dedicated specifically to pedagogical approaches for teaching data mining, and educational programs have remained primarily within Computer Science departments, often targeting graduate students. This paper presents the findings of an examination into the teaching of data mining concepts to undergraduates. The research was conducted by delivering an Association Rules lesson to 86 student participants. The participants received the lesson through either a Direct Instruction or a Concept Attainment teaching approach. <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T-tests</i> and <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ANOVA</i> determined if significant differences existed between the scores generated under the two teaching models and within Kolb's four learning styles. The findings show that effectively teaching data mining concepts to the target audience is not as simple as choosing one teaching methodology over another or targeting a specific learning style group. The results also indicate that data mining concepts and techniques can be effectively taught to the target audience.